Alternatives and similar repositories for PRIME

Users that are interested in PRIME are comparing it to the libraries listed below

• Open-Reasoner-Zero / Open-Reasoner-Zero
  Official Repo for Open-Reasoner-Zero
  ☆2,079Updated 6 months ago
• mll-lab-nu / RAGEN
  RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
  ☆2,442Updated 2 weeks ago
• openreasoner / openr
  OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
  ☆1,830Updated 11 months ago
• SimpleBerry / LLaMA-O1
  Large Reasoning Models
  ☆806Updated last year
• GAIR-NLP / O1-Journey
  O1 Replication Journey
  ☆2,001Updated 11 months ago
• BytedTsinghua-SIA / DAPO
  An Open-source RL System from ByteDance Seed and Tsinghua AIR
  ☆1,667Updated 7 months ago
• Open-Source-O1 / Open-O1
  ☆1,345Updated last year
• GAIR-NLP / LIMO
  [COLM 2025] LIMO: Less is More for Reasoning
  ☆1,056Updated 4 months ago
• AIDC-AI / Marco-o1
  An Open Large Reasoning Model for Real-World Solutions
  ☆1,538Updated 6 months ago
• zhentingqi / rStar
  ☆969Updated 10 months ago
• hkust-nlp / simpleRL-reason
  Simple RL training for reasoning
  ☆3,808Updated 4 months ago
• huggingface / Math-Verify
  ☆1,035Updated 5 months ago
• Qihoo360 / Light-R1
  ☆754Updated 3 months ago
• microsoft / rStar
  ☆1,357Updated 3 months ago
• Agent-RL / ReCall
  ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
  ☆1,262Updated 7 months ago
• PeterGriffinJin / Search-R1
  Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
  ☆3,649Updated last month
• sail-sg / understand-r1-zero
  Understanding R1-Zero-Like Training: A Critical Perspective
  ☆1,173Updated 3 months ago
• inclusionAI / AReaL
  Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
  ☆3,201Updated this week
• princeton-nlp / SimPO
  [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
  ☆934Updated 10 months ago
• THUDM / slime
  slime is an LLM post-training framework for RL Scaling.
  ☆2,911Updated this week
• rllm-org / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆4,854Updated last week
• open-thoughts / open-thoughts
  Fully open data curation for reasoning models
  ☆2,170Updated 2 weeks ago
• lsdefine / simple_GRPO
  A very simple GRPO implement for reproducing r1-like LLM thinking.
  ☆1,499Updated last month
• ByteDance-Seed / Seed-Thinking-v1.5
  ☆818Updated 6 months ago
• RUCAIBox / Slow_Thinking_with_LLMs
  A series of technical report on Slow Thinking with LLM
  ☆753Updated 4 months ago
• MoonshotAI / Moonlight
  Muon is Scalable for LLM Training
  ☆1,380Updated 4 months ago
• Unakar / Logic-RL
  Reproduce R1 Zero on Logic Puzzle
  ☆2,416Updated 9 months ago
• THUDM / ReST-MCTS
  ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)
  ☆686Updated 11 months ago
• huggingface / search-and-learn
  Recipes to scale inference-time compute of open models
  ☆1,120Updated 7 months ago
• PRIME-RL / TTRL
  [NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
  ☆926Updated 2 months ago